Abreu Andre Boavida, Universidade Nacional Timor-Lorosae, Japan

This research uses a multiclass deep learning model to identify images containing different mikrolet vehicles. In addition, we have studied multiclass classification research by assessing the performance of mikroletpictures with the same color and comparing the classification performance of several proposed deep learning models. The objectives of this study are two-fold: first, to identify images containing different mikrolet vehicle lanes, and second, compare four deep learning models for evaluation of the accuracy of performance precision, recall, f1-measure, micro and macro average ROC curves areas.

Deep Learning Models, Classification, Mikrolet, Multiclass, Vehicles, ROC